(Universiti Teknologi MARA (UiTM) Shah Alam, Malaysia)(2) Noor Aida Syakira Ahmad Sabri
(Universiti Teknologi MARA (UiTM) Shah Alam, Malaysia)(3) Muhammad Ikhsan Roslan
(Universiti Teknologi MARA (UiTM) Shah Alam, Malaysia)(4) Nurlaila Ismail
(Universiti Teknologi MARA (UiTM) Shah Alam, Malaysia)(5) Zakiah Mohd Yusoff
(Universiti Teknologi MARA (UiTM) Shah Alam, Malaysia)(6) Mohd Nasir Taib
(Universiti Teknologi MARA (UiTM) Shah Alam, Malaysia)*corresponding author
AbstractAgarwood, derived from the Aquilaria species, is among the most valuable aromatic resources, yet frequent species misidentification hampers conservation efforts and compliance with trade regulations. This study applied a chemometric ANN framework to classify four Aquilaria species (A. malaccensis, A. beccariana, A. subintegra, and A. crassna) based on essential oil composition. A total of 720 samples (180 per species, each analyzed in triplicate) were extracted by hydrodistillation and profiled using GC–MS coupled to GC–FID. Six compounds were consistently detected, and three (δ-guaiene, 10-epi-γ-eudesmol, γ-eudesmol) were retained for classification based on ≥95% detection frequency and >0.2% relative abundance. Pearson correlation guided feature selection, and ANN models were trained using both a 70:15:15 train–validation–test split and stratified 5-fold cross-validation with 1000 bootstrap resamples. The optimized network achieved near-perfect performance, with a mean accuracy of ~99.8% (95% CI: 99.6–100.0), and precision, recall, and F1 scores all exceeding 99.5%. In comparison, bootstrapped confidence intervals were tightly bounded at 100%, confirming robustness against data leakage. These findings demonstrate that correlation-guided feature selection combined with ANN modeling enables reproducible and highly accurate species authentication, offering a practical framework for integration into agarwood quality control, conservation monitoring, and international trade compliance.
KeywordsAgarwood; Aquilaria species; Pearson correlation; Artificial Neural Network (ANN); Classification model
|
DOIhttps://doi.org/10.26555/ijain.v11i4.2141 |
Article metricsAbstract views : 301 | PDF views : 19 |
Cite |
Full Text Download
|
References
[1] P. Shivanand, N. F. Arbie, S. Krishnamoorthy, and N. Ahmad, “Agarwood—The Fragrant Molecules of a Wounded Tree,” Molecules, vol. 27, no. 11, p. 3386, May 2022, doi: 10.3390/molecules27113386.
[2] S. Y. Lee, M. Turjaman, and R. Mohamed, “Phylogenetic Relatedness of Several Agarwood-Producing Taxa (Thymelaeaceae) from Indonesia,” Trop. Life Sci. Res., vol. 29, no. 2, pp. 13–28, 2018, doi: 10.21315/tlsr2018.29.2.2.
[3] A. Nor Mazila Ramli, S. Yusof, P. Bhuyar, A. W. Aminan, and S. N. Tajuddin, “Fungi mediated agarwood (A. malaccensis) production and their pharmaceutical applications: A systematic review,” Int. J. Plant Based Pharm., vol. 2, no. 2, pp. 261–270, Sep. 2022, doi: 10.29228/ijpbp.8.
[4] N. A. Syafiqah Noramli, N. A. S. Ahmad Sabri, M. I. Roslan, N. Ismail, Z. M. Yusoff, and M. N. Taib, “Unraveling the relationships among essential oil compounds in Aquilaria species using GC-MS and GC-FID techniques,” Indones. J. Electr. Eng. Comput. Sci., vol. 39, no. 1, p. 167, Jul. 2025, doi: 10.11591/ijeecs.v39.i1.pp167-177.
[5] J. M. R. Alamil et al., “Rediscovering the Therapeutic Potential of Agarwood in the Management of Chronic Inflammatory Diseases,” Molecules, vol. 27, no. 9, p. 3038, May 2022, doi: 10.3390/molecules27093038.
[6] P. Zhang, X. Li, Z. Cui, and D. Xu, “Morphological, physiological, biochemical and molecular analyses reveal wounding-induced agarwood formation mechanism in two types of Aquilaria sinensis (Lour.) Spreng,” Ind. Crops Prod., vol. 178, p. 114603, Apr. 2022, doi: 10.1016/j.indcrop.2022.114603.
[7] F. A. Abdul Kadir, K. A. Azizan, and R. Othman, “Transcriptome of Aquilaria malaccensis containing agarwood formed naturally and induced artificially,” BMC Res. Notes, vol. 14, no. 1, p. 117, Dec. 2021, doi: 10.1186/s13104-021-05532-9.
[8] Y. Van Thi et al., “An Updated Review of Aquilaria Species: Distribution, Chemical Constituents and Authentication Methods,” Asian J. Plant Sci., vol. 23, no. 2, pp. 146–167, Mar. 2024, doi: 10.3923/ajps.2024.146.167.
[9] Z. Zhang et al., “Fusarium oxysporum infection-induced formation of agarwood (FOIFA): A rapid and efficient method for inducing the production of high quality agarwood,” PLoS One, vol. 17, no. 11, p. e0277136, Nov. 2022, doi: 10.1371/journal.pone.0277136.
[10] X. Zhang et al., “Sesquiterpenoids in Agarwood: Biosynthesis, Microbial Induction, and Pharmacological Activities,” J. Agric. Food Chem., vol. 72, no. 42, pp. 23039–23052, Oct. 2024, doi: 10.1021/acs.jafc.4c06383.
[11] S. Y. Lee, D. U. Lamasudin, and R. Mohamed, “Rapid detection of several endangered agarwood-producing Aquilaria species and their potential adulterants using plant DNA barcodes coupled with high-resolution melting (Bar-HRM) analysis,” Holzforschung, vol. 73, no. 5, pp. 435–444, May 2019, doi: 10.1515/hf-2018-0149.
[12] M. A. Ullah, “Boosting up the economy of Pakistan through agarwood production,” Int. J. Hortic. Food Sci., vol. 2, no. 2, pp. 25–35, Jul. 2020, doi: 10.33545/26631067.2020.v2.i2a.49.
[13] T. Lim and M. Turjaman, “Expensive, Exploited and Endangered. A Review of the Agarwood-Producing Genera Aquilaria and Gyrinops: CITES considerations, Trade Patterns, Conservation, and Management,” vol. 12, no. June. pp. 14–25, 2022, [Online]. Available: https://share.google/5vqgUEv0OdumjWRCs.
[14] S. Y. Lee and R. Mohamed, “The Origin and Domestication of Aquilaria, an Important Agarwood-Producing Genus,” in Tropical Forestry, Springer, Singapore, 2016, pp. 1–20, doi: 10.1007/978-981-10-0833-7_1 .
[15] G. Schomburg, “Two-dimensional gas chromatography: Principles, instrumentation, methods,” J. Chromatogr. A, vol. 703, no. 1–2, pp. 309–325, Jun. 1995, doi: 10.1016/0021-9673(95)00190-X.
[16] Z. M. Yusoff and N. Ismail, “Datasets of chemical compounds in three different species of aquilaria using GC-MS coupled with GC-FID analysis,” Data Br., vol. 53, p. 110209, Apr. 2024, doi: 10.1016/j.dib.2024.110209.
[17] T. R. Rao, S. Harshitha, and K. L. Lahari, “Gas Chromatography-Mass Spectroscopy: An Overview,” Eur. J. Biomed., vol. 10, no. 5, pp. 83–89, 2023, [Online]. Available at: https://www.researchgate.net/profile/Rama-Tadikonda/publication/371989508.
[18] S. S.S.S.M, V. Atyam, M. Avidi, and D. Ayinala, “A Review on Gas chromatography – Mass spectroscopy: Short Communication,” J. Pharma Insights Res., vol. 2, no. 1, pp. 009–013, Feb. 2024. [Online]. Available at: https://jopir.in/index.php/journals/article/view/70.
[19] J. Y.-L. Chan et al., “Mitigating the Multicollinearity Problem and Its Machine Learning Approach: A Review,” Mathematics, vol. 10, no. 8, p. 1283, Apr. 2022, doi: 10.3390/math10081283.
[20] M. Sokolova and G. Lapalme, “A systematic analysis of performance measures for classification tasks,” Inf. Process. Manag., vol. 45, no. 4, pp. 427–437, Jul. 2009, doi: 10.1016/j.ipm.2009.03.002.
[21] A. Shuttleworth and S. D. Johnson, “GC-MS/FID/EAD: A method for combining mass spectrometry with gas chromatography-electroantennographic detection,” Front. Ecol. Evol., vol. 10, p. 1042732, Dec. 2022, doi: 10.3389/fevo.2022.1042732.
[22] Y. Sundaraj, A. Mediani, K. F. Rodrigues, and S. N. Baharum, “GC-MS olfactometry reveals sesquiterpenes α-humulene and δ-cadinene significantly influence the aroma of treated Aquilaria malaccensis essential oil,” Aust. J. Crop Sci., vol. 17, no. 17(12):2023, pp. 893–901, Dec. 2023, doi: 10.21475/ajcs.23.17.12.p3916.
[23] N. Ismail, “Analysis of GC-FID and GC-MS Microwave-Assisted Hydrodistillation Extraction (MAHD) of Agarwood Chips,” Int. J. Integr. Eng., vol. 13, no. 6, pp. 180–189, Aug. 2021, doi: 10.30880/ijie.2021.13.06.017.
[24] R. Chattamvelli, “Pearson’s Correlation,” in Correlation in Engineering and the Applied Sciences, Springer, Cham, 2024, pp. 55–76, doi: 10.1007/978-3-031-51015-1_2.
[25] S. N. Selamat, N. A. Majid, and M. R. Taha, “Multicollinearity and spatial correlation analysis of landslide conditioning factors in Langat River Basin, Selangor,” Nat. Hazards, vol. 121, no. 3, pp. 2665–2684, Feb. 2025, doi: 10.1007/s11069-024-06903-8.
[26] S. Kumar and P. Rani, “An AI-based Liver Disease Prediction Model based on Pearson Correlation Feature Selection Method,” Biomed. Pharmacol. J., vol. 17, no. 4, pp. 2187–2202, Dec. 2024, doi: 10.13005/bpj/3016.
[27] C. A. Rickert, M. Henkel, and O. Lieleg, “An efficiency-driven, correlation-based feature elimination strategy for small datasets,” APL Mach. Learn., vol. 1, no. 1, Mar. 2023, doi: 10.1063/5.0118207.
[28] S. Jiang et al., “Rock slope displacement prediction based on multi-source information fusion and SSA-DELM model,” Front. Environ. Sci., vol. 10, p. 982069, Sep. 2022, doi: 10.3389/fenvs.2022.982069.
[29] Et. al., Alhassan Umar Ahmad, “A Study of Multicollinearity Detection and Rectification under Missing Values,” Turkish J. Comput. Math. Educ., vol. 12, no. 1S, pp. 399–418, Apr. 2021, doi: 10.17762/turcomat.v12i1S.1880.
[30] J. H. Kim, “Multicollinearity and misleading statistical results,” Korean J. Anesthesiol., vol. 72, no. 6, pp. 558–569, Dec. 2019, doi: 10.4097/kja.19087.
[31] I. Carev et al., “Centaurea triumfetii essential oil chemical composition, comparative analysis, and antimicrobial activity of selected compounds,” Sci. Rep., vol. 13, no. 1, p. 7475, May 2023, doi: 10.1038/s41598-023-34058-2.
[32] H. Oghenekevwe Etaga, R. Chibotu Ndubisi, and N. Lilian Oluebube, “Effect of Multicollinearity on Variable Selection in Multiple Regression,” Sci. J. Appl. Math. Stat., vol. 9, no. 6, p. 141, Dec. 2021, doi: 10.11648/j.sjams.20210906.12.
[33] T. Kyriazos and M. Poga, “Dealing with Multicollinearity in Factor Analysis: The Problem, Detections, and Solutions,” Open J. Stat., vol. 13, no. 03, pp. 404–424, Jun. 2023, doi: 10.4236/ojs.2023.133020.
[34] N. Shchurov, I. Isaev, S. Burikov, T. Dolenko, K. Laptinskiy, and S. Dolenko, “Taking into Account Mutual Correlations during Selection of Significant Input Features in Neural Network Solution of Inverse Problems of Spectroscopy,” in Proceedings of The 6th International Workshop on Deep Learning in Computational Physics — PoS(DLCP2022), Nov. 2022, vol. 429, p. 026, doi: 10.22323/1.429.0026.
[35] N. Z. Mahabob, Z. M. Yusoff, A. F. Mohd Amidon, N. Ismail, and M. N. Taib, “A novel application of artificial neural network for classifying agarwood essential oil quality,” Int. J. Electr. Comput. Eng., vol. 12, no. 6, p. 6645, Dec. 2022, doi: 10.11591/ijece.v12i6.pp6645-6652.
[36] A. H. Zaidi et al., “Statistical analysis of agarwood oil chemical compound exists in four species of Aquilaria,” Int. J. Adv. Appl. Sci., vol. 13, no. 3, p. 727, Sep. 2024, doi: 10.11591/ijaas.v13.i3.pp727-732.
[37] N. A. S. Noramli, N. A. S. A. Sabri, M. I. Roslan, N. Ismail, Z. M. Yusoff, and M. N. Taib, “Analytical Characterization of Aquilaria Species Essential Oils Using Advanced Chromatographic Techniques Based on GC-MS and GC-FID,” in 2025 21st IEEE International Colloquium on Signal Processing & Its Applications (CSPA), Feb. 2025, no. 2025, pp. 10–15, doi: 10.1109/CSPA64953.2025.10933407.
[38] M. Mohamad et al., “kNN: Classification of Agarwood Types in Oil and Wooden Using E-nose,” in Lecture Notes in Electrical Engineering, vol. 842, Springer, Singapore, 2022, pp. 575–586, doi: 10.1007/978-981-16-8690-0_52.
[39] D. Yogapriya and M. Uma, “Agarwood Grade Estimation Procedure using Cnn and Sculpture Automation,” in 2023 2nd International Conference on Edge Computing and Applications (ICECAA), Jul. 2023, pp. 1185–1191, doi: 10.1109/ICECAA58104.2023.10212367.
[40] S. Lotthar et al., “Decision Tree on Branch Node Observations for Significant Compounds of Agarwood Oil Different Grades,” J. Tomogr. Syst. Sens. Appl., vol. 6, no. 1, pp. 43–51, Jun. 2023. [Online]. Available at: http://tssa.my/index.php/jtssa/article/view/207.
[41] F. Haqqi, M. Rivai, and T. Mujiono, “Agarwood Classification using the Electronic Nose Method,” in 2024 International Seminar on Intelligent Technology and Its Applications (ISITIA), Jul. 2024, no. 2024, pp. 396–400, doi: 10.1109/ISITIA63062.2024.10667957.
[42] Y. Pang et al., “Solid-Phase Microextraction/Gas Chromatography–Time-of-Flight Mass Spectrometry Approach Combined with Network Pharmacology Analysis to Evaluate the Quality of Agarwood from Different Regions against Anxiety Disorder,” Molecules, vol. 29, no. 2, p. 468, Jan. 2024, doi: 10.3390/MOLECULES29020468/S1.
[43] R. Hayati, A. A. Munawar, E. Lukitaningsih, N. Earlia, T. Karma, and R. Idroes, “Combination of PCA with LDA and SVM classifiers: A model for determining the geographical origin of coconut in the coastal plantation, Aceh Province, Indonesia,” Case Stud. Chem. Environ. Eng., vol. 9, p. 100552, Jun. 2024, doi: 10.1016/j.cscee.2023.100552.
[44] N. Zawani Mahabob, Z. M. Yusoff, A. F. Mohd Amidon, N. Ismail, and M. Nasir Taib, “Modeling of agarwood oil compounds based on linear regression and ANN for oil quality classification,” Int. J. Electr. Comput. Eng., vol. 11, no. 6, p. 5505, Dec. 2021, doi: 10.11591/ijece.v11i6.pp5505-5514.
[45] N. Zawani Mahabob, A. F. Mohd Amidon, Z. Mohd Yusoff, N. Ismail, and S. N. Tajjudin, “Comparison of ANN Performance Towards Agarwood Oil Compounds Pre-processing Based on Principal Component Analysis (PCA) and Stepwise Regression Selection Method,” J. Electr. Electron. Syst. Res., vol. 19, no. OCT2021, pp. 51–55, Oct. 2021, doi: 10.24191/jeesr.v19i1.007.
[46] T. S. Hong, F. Hanim Hashim, T. Raj, and A. B. Huddin, “Classification of Oil Palm Fruit Ripeness Using Artificial Neural Network,” in 2021 IEEE International Conference on Automatic Control & Intelligent Systems (I2CACIS), Jun. 2021, pp. 358–363, doi: 10.1109/I2CACIS52118.2021.9495857.
[47] S. M. H. Mohd Huzir, S. N. Tajuddin, Z. Mohd Yusoff, N. Ismail, A. A. Almisreb, and M. N. Taib, “Agarwood oil quality identification using artificial neural network modelling for five grades,” Int. J. Electr. Comput. Eng., vol. 14, no. 2, p. 2254, Apr. 2024, doi: 10.11591/ijece.v14i2.pp2254-2261.
[48] Aqib Fawwaz Mohd Amidon, Zakiah Mohd Yusoff, Nurlaila Ismail, and Mohd Nasir Taib, “KNN Euclidean Distance Model Performance on Aquilaria Malaccensis Oil Qualities,” J. Adv. Res. Appl. Sci. Eng. Technol., vol. 48, no. 2, pp. 16–28, Jul. 2024, doi: 10.37934/araset.48.2.1628.
[49] Ö. Şimşek, “Machine Learning Offers Insights into the Impact of In Vitro Drought Stress on Strawberry Cultivars,” Agriculture, vol. 14, no. 2, p. 294, Feb. 2024, doi: 10.3390/agriculture14020294.
[50] Z.-Q. Xie, J.-Y. Xu, M. Rafiq, and C.-S. Cheng, “An analysis of Agarwood trade patterns, historical perspectives, and species identification challenges: repercussions for importing nations,” TMR Mod. Herb. Med., vol. 7, no. 1, p. 1, 2024, doi: 10.53388/MHM2024001.
[51] Y. Z. H.-Y. Hashim et al., “A Bibliometric Analysis of Agarwood Research, 1959-2021,” J. Agrobiotechnology, vol. 13, no. 2, pp. 37–64, Nov. 2022, doi: 10.37231/jab.2022.13.2.296.
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
___________________________________________________________
International Journal of Advances in Intelligent Informatics
ISSN 2442-6571 (print) | 2548-3161 (online)
Organized by UAD and ASCEE Computer Society
Published by Universitas Ahmad Dahlan
W: http://ijain.org
E: info@ijain.org (paper handling issues)
andri.pranolo.id@ieee.org (publication issues)
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0